Spectral Modeling Synthesis

By Xavier Serra, Julius Orion Smith III. 1990

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Jesse Engel
2. Lamtharn Hantrakul
3. Adam Roberts
4. Chenjie Gu
5. Mark B. Sandler
6. Juan Pablo Bello
7. Colin Raffel
8. Yannis Agiomyrgiannakis

Citations in the corpus

• DDSP: Differentiable Digital Signal Processing (2020, methodology): “One of the reasons that SMS is more expressive than many other parametric models because it has so many more parameters.”
• Vocaine the vocoder and applications in speech synthesis (2015, methodology): “Similar notable work was made by the audio processing community with the Sinusoids-plus-Noise model [7] and IRCAM’s Super Vocoder Phase [8].”
• A tutorial on onset detection in music signals (2005, methodology): “Amongst these methods, spectral modeling synthesis (SMS) [8] explicitly considers the residual1 of the synthesis method as a Gaussian white noise filtered with a slowly varying low-order filter.”